Hugging Face's logo

gokuls
/
bert_12_layer_model_v1_complete_training

Fill-Mask
Transformers
PyTorch
TensorBoard
hybridbert
Generated from Trainer
Model card Files
xet
 Metrics Community
gokuls commited on
Commit
cc50a7e
·
1 Parent(s): 3d6eaf2

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +104 -0
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - accuracy
6
+ model-index:
7
+ - name: bert_12_layer_model_v1_complete_training
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # bert_12_layer_model_v1_complete_training
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.7148
19
+ - Accuracy: 0.6576
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 64
40
+ - eval_batch_size: 64
41
+ - seed: 10
42
+ - distributed_type: multi-GPU
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 10000
46
+ - num_epochs: 5
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:------:|:---------------:|:--------:|
52
+ | 6.1779 | 0.11 | 10000 | 6.1719 | 0.1487 |
53
+ | 4.6914 | 0.22 | 20000 | 4.5039 | 0.3178 |
54
+ | 3.2325 | 0.33 | 30000 | 3.0977 | 0.4772 |
55
+ | 2.831 | 0.44 | 40000 | 2.7266 | 0.5224 |
56
+ | 2.6262 | 0.55 | 50000 | 2.5371 | 0.5455 |
57
+ | 2.5006 | 0.66 | 60000 | 2.4141 | 0.5614 |
58
+ | 2.4062 | 0.76 | 70000 | 2.3242 | 0.5734 |
59
+ | 2.3338 | 0.87 | 80000 | 2.2539 | 0.5823 |
60
+ | 2.2838 | 0.98 | 90000 | 2.2012 | 0.5894 |
61
+ | 2.231 | 1.09 | 100000 | 2.1504 | 0.5959 |
62
+ | 2.1903 | 1.2 | 110000 | 2.1133 | 0.6009 |
63
+ | 2.1594 | 1.31 | 120000 | 2.0801 | 0.6054 |
64
+ | 2.1307 | 1.42 | 130000 | 2.0488 | 0.6095 |
65
+ | 2.0948 | 1.53 | 140000 | 2.0234 | 0.6133 |
66
+ | 2.0748 | 1.64 | 150000 | 1.9980 | 0.6169 |
67
+ | 2.0572 | 1.75 | 160000 | 1.9756 | 0.6195 |
68
+ | 2.0359 | 1.86 | 170000 | 1.9551 | 0.6225 |
69
+ | 2.0148 | 1.97 | 180000 | 1.9385 | 0.6251 |
70
+ | 1.9994 | 2.08 | 190000 | 1.9219 | 0.6274 |
71
+ | 1.9769 | 2.18 | 200000 | 1.9043 | 0.6297 |
72
+ | 1.9705 | 2.29 | 210000 | 1.8916 | 0.6317 |
73
+ | 1.9557 | 2.4 | 220000 | 1.8779 | 0.6338 |
74
+ | 1.9407 | 2.51 | 230000 | 1.8643 | 0.6354 |
75
+ | 1.9307 | 2.62 | 240000 | 1.8525 | 0.6372 |
76
+ | 1.9186 | 2.73 | 250000 | 1.8408 | 0.6388 |
77
+ | 1.9114 | 2.84 | 260000 | 1.8320 | 0.6401 |
78
+ | 1.896 | 2.95 | 270000 | 1.8213 | 0.6419 |
79
+ | 1.8857 | 3.06 | 280000 | 1.8115 | 0.6433 |
80
+ | 1.8752 | 3.17 | 290000 | 1.8037 | 0.6443 |
81
+ | 1.8662 | 3.28 | 300000 | 1.7949 | 0.6457 |
82
+ | 1.8575 | 3.39 | 310000 | 1.7871 | 0.6470 |
83
+ | 1.8538 | 3.5 | 320000 | 1.7793 | 0.6478 |
84
+ | 1.8426 | 3.6 | 330000 | 1.7734 | 0.6489 |
85
+ | 1.8389 | 3.71 | 340000 | 1.7646 | 0.6501 |
86
+ | 1.8278 | 3.82 | 350000 | 1.7598 | 0.6511 |
87
+ | 1.8319 | 3.93 | 360000 | 1.7529 | 0.6520 |
88
+ | 1.8203 | 4.04 | 370000 | 1.7471 | 0.6527 |
89
+ | 1.8162 | 4.15 | 380000 | 1.7412 | 0.6536 |
90
+ | 1.8113 | 4.26 | 390000 | 1.7373 | 0.6543 |
91
+ | 1.8055 | 4.37 | 400000 | 1.7324 | 0.6551 |
92
+ | 1.7991 | 4.48 | 410000 | 1.7285 | 0.6556 |
93
+ | 1.7965 | 4.59 | 420000 | 1.7246 | 0.6562 |
94
+ | 1.7938 | 4.7 | 430000 | 1.7207 | 0.6567 |
95
+ | 1.793 | 4.81 | 440000 | 1.7178 | 0.6571 |
96
+ | 1.7848 | 4.92 | 450000 | 1.7148 | 0.6576 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - Transformers 4.26.1
102
+ - Pytorch 1.14.0a0+410ce96
103
+ - Datasets 2.10.1
104
+ - Tokenizers 0.13.2